Prathmesh Patel

You can test your server against every protocol version across all client registration methods. My personal favorite feature since it dropped in October. Check it out here tinyurl.com/mcpjamoauthx

If you want to debug Oauth with UI we’ve got you too! In my last post, an agent used the MCPJam CLI to find and fix an OAuth client registration issue. Here’s the same workflow using MCPJam’s OAuth Debugger: every step of the MCP OAuth flow is logged, tied back to the spec, and mapped out in the UI. When something fails, you can see exactly which part of the flow broke. #mcp #modelcontextprotocol #oauth

In this example, the server fails for dynamic client registration. MCPJam surfaces the raw error, points to the failed OAuth step, and lets you rerun the flow until the server connects.

@chelo_jimenez22 @mcpjams Best of both worlds

@Prathmeshp_16 @mcpjams Oauth Debugger in your terminal!

This is what agent-native MCP debugging looks like. In this demo, a coding agent uses our @mcpjams CLI to connect to an MCP server, identify a client registration issue, help the developer fix it, then run protocol and OAuth conformance checks. #mcp #modelcontextprotocol #cli #oauth

@mcpjams OAuth AS used for the demo: @stytchauth

@mcpjams Check out docs here: tinyurl.com/mcpjamclix Install with one line: npm i -g @mcpjam/cli

@chelo_jimenez22 @mcpjams 🤝

@Prathmeshp_16 @mcpjams Agents 🤝 MCP Apps

Show agents your MCP Apps UI with: mcpjam tools call --ui Coding agents can call a tool and see its UI rendered live in @mcpjams Inspector. Agents can inspect more than JSON now. They can validate the actual user interfaces your end-users will see. Install the CLI here: tinyurl.com/mcpjamclix #mcp #modelcontextprotocol #cli #mcpjam

Inspect your MCP servers today with one command: mcpjam Our new @mcpjams CLI brings core Inspector workflows to your terminal: connect to servers, call tools, debug OAuth, and run protocol conformance. It also lets your coding agent debug MCP Apps by rendering tool results in the MCPJam UI! Pair it with our skill and get jamming: docs.mcpjam.com/cli/overview npm i -g @mcpjam/cli #mcp #modelcontextprotocol #cli

You’re essentially “tricking” an agent to provide you additional user context directly from their platform: you can see how that could be seen as a data exfiltration risk from a security PoV. Not to put words in anyone’s mouth: I’m sure they’d also love to charge companies integrating with them about what users are actually doing with their products. A few angles there.

Awesome insights 🚀 getting right at the problem of the agent cannibalizing user context. Adding parameter is a great solve initially, but we've gotten signal it won't be condoned by the larger agent apps (ChatGPT, Claude). I wrote about the problem broadly in Effective MCP: mcpjam.com/blog/effective…

- Bundle Skills + MCP to make your MCP server more efficient with plugins: perhaps, though yet another variable for an MCP server team to evaluate their server on now. Solve the MxN connection problem, but lets not forget the growing variables to evaluate a server's efficacy

Solid high-level read. Personal takeaways: A great Day-1 guide on MCP tool design and best practices - but MCP client leaning as it doesn't address some immediate problems MCP servers will face in actually testing for natural questions that come with e.g. "but how do I know Skills + MCP is actually more effective for my server"? claude.com/blog/building-…

...Buts: - The post calls MCP "the compounding layer." True for the ecosystem: a server built today works with clients that don't exist yet. The distribution of compounding value is skewed toward whoever owns the host/client. More servers/integrations to connect to, more user intent and context, more capabilities they can decide to expose. With each client bringing with it its own discovery, selection logic, capabilities (skills + mcp as plugins), the cardinality of variables that an MCP server team needs to evaluate their server for continues to increase.

Some highlights: - MCP SDK downloads: 300M/month, up from 100M at the start of 2026 -> cool! wonder how much of this is agent-driven - Core tool design: every tool call is a decision point for the agent. Reduce the # of tool calls to reach your desired user flow. e.g. Cloudflare exposes 2 tools that end up exposing 2,500+ endpoints in ~1k tokens used on defs - Solid methods for clients to reduce tool-definition token consumption (though not baked in the spec)

connect your MCP server → see a trace in 30 seconds tool calls, args, latency → all captured the moment you run. demo ↓ #mcp #modelcontextprotocol